# Value Separation in Pebble: Storage Engine Optimization

DevFeed: [Value Separation in Pebble: Storage Engine Optimization](<https://devfeed.tech/articles/value-separation-in-pebble-storage-engine-optimization-23821.md>)

Original publisher: [Read original article](<https://cockroachlabs.com/blog/value-separation-pebble-optimization>)

Author: Jackson Owens,Annie Pompa

Published: 2026-01-13T00:00:00Z

Content type: article

Language: en

Sources: [Cockroach Labs](<https://devfeed.tech/sources/cockroach-labs.md>)

Topics: [Optimization](<https://devfeed.tech/topics/optimization.md>), [CockroachDB](<https://devfeed.tech/topics/cockroachdb.md>), [Database](<https://devfeed.tech/topics/database.md>), [IO](<https://devfeed.tech/topics/io.md>), [benchmarking](<https://devfeed.tech/topics/benchmarking.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cockroachdb](<https://devfeed.tech/tags/cockroachdb.md>), [database](<https://devfeed.tech/tags/database.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [performance](<https://devfeed.tech/tags/performance.md>), [storage](<https://devfeed.tech/tags/storage.md>)

## AI overview

This article explains how value separation in Pebble, CockroachDB's key-value storage engine, reduces redundant I/O during compaction. Introduced in CockroachDB v25.4, the optimization can improve storage-engine throughput by up to approximately 50% depending on the workload.

## Source excerpt

At its foundation, CockroachDB depends on a key-value storage engine called Pebble. In CockroachDB v25.4, the storage team introduced value separation within Pebble: an optimization that improves compaction efficiency for many workloads. Value separation increases the throughput of the core of CockroachDB, the storage engine, by up to ~50%, depending on the workload, through algorithmic improvements. It reduces redundant I/O, reducing cost-to-serve at scale. We'll look at how Pebble represents data today, what's changed, and how that translates to database efficiency.